Training in progress, step 185

README.md

@@ -1,18 +1,17 @@
 ---
 base_model: openai/gpt-oss-20b
-datasets: HuggingFaceH4/Multilingual-Thinking
 library_name: transformers
 model_name: DepressLLM
 tags:
 - generated_from_trainer
-- trl
 - sft
+- trl
 licence: license
 ---
 
 # Model Card for DepressLLM
 
-This model is a fine-tuned version of [openai/gpt-oss-20b](https://huggingface.co/openai/gpt-oss-20b) on the [HuggingFaceH4/Multilingual-Thinking](https://huggingface.co/datasets/HuggingFaceH4/Multilingual-Thinking) dataset.
+This model is a fine-tuned version of [openai/gpt-oss-20b](https://huggingface.co/openai/gpt-oss-20b).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start

adapter_config.json

@@ -28,10 +28,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
     "q_proj",
     "v_proj",
-    "k_proj"
+    "k_proj",
+    "o_proj"
   ],
   "target_parameters": [
     "7.mlp.experts.gate_up_proj",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e2a0610fc6f7a47dc24a4b060e84720c209d0ea3b405eefe54351ee01126309
+oid sha256:273410ba07af830e1c9888ed2084164a16f79b9e6ba47490d32b3dd5b1490b9c
 size 60189176

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7a868ecee843654f05b5d7f0baf9ce7016a423e155c57a1bdb3d78e71ce6f43
+oid sha256:a94c02ab6a320722bf28ba3855d74f8b538c96e0de30d26b6c536678914b7b16
 size 6161